[KongchangAI]
Model

Sonic

A model name mentioned in the text; specific details are not elaborated.

Timeline (last 90 days)

Nov 16

By Artificial Analysis per-task cost, Sonic's highest tier is 10.2 dollars per task and Hydrogen's highest tier is 3.16 dollars per task; Tera is cheaper than Hydrogen but has a lower top score.

Unverified50%
Nov 16

In the Automation Bench test, Hydrogen scored about 76%, Sonic 72%, and Tera 60%.

Unverified50%
Nov 16

In the MKA visual file test, Hydrogen scored about 53%, Sonic 52%, and Tera about 44%.

Unverified50%
Nov 16

In the OS World 2.1 test, Hydrogen was slightly worse than Sonic.

Unverified50%
Nov 16

In the Suesway code test, Hydrogen scored 13.5, Tera scored 8, and Sonic scored 3.

Unverified50%
Nov 16

In the Agent's Last Exam test, Hydrogen scored close to 72%, Tera slightly below 70%, and Sonic about 60%.

Unverified50%
Nov 14

Google officially benchmarked Hydrogen against Sonic and Terra, and Hydrogen surpassed Sonic and Terra on many benchmark tests.

Unverified50%
Oct 17

The official documentation states that HiQ 5.5 is better suited to narrow-scope tasks, and Sonic or Opus is recommended for complex programming tasks.

Unverified50%
Oct 5

Anthropic's three product lines—Fable, Opus, and Sonic—have reportedly been secretly tested on different accounts.

Expired50%

All Facts (8)

Source Articles